© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 7-RES-JB
    11. 3599
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the ability to do something or take action

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements expressing capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    interstitial
    -0.63
     caution
    -0.63
     Falling
    -0.63
     regretted
    -0.61
     IB
    -0.60
     questioning
    -0.60
    EStreamFrame
    -0.58
    path
    -0.58
    estern
    -0.57
    ãĥ´ãĤ¡
    -0.57
    POSITIVE LOGITS
    't
    1.15
     afford
    1.14
     muster
    0.91
     convince
    0.88
    adian
    0.83
    utils
    0.82
    ipeg
    0.81
     survive
    0.78
     spare
    0.77
     persuade
    0.76
    Activations Density 0.096%

    No Known Activations